• de

PD Dr. Haojin Yang

Head of Multimedia and Machine Learning Research Group

Hasso Plattner Institute for Digital Engineering gGmbH
Prof.-Dr.-Helmert-Str. 2-3
14482 Potsdam

fax:         +49 (0)331-5509-3511
email:     haojin.yang(at)hpi.de

Google Scholar DBLP

Website of Multimedia and Machine Learning Research Group

Research Interests

Efficient AI, Edge AI, deep model acceleration and compression, computer vision applications, lecture video indexing.

Multimedia Analysis with Deep Learning

Learning and understanding multimedia content is a challenging task in the research field of information retrieval and multimedia analysis. Deep Learning (DL), as a new area of machine learning (since 2006), has already been impacting a wide range of multimedia information processing. Recently, the techniques developed based on DL achieved substantial progress in fields including Speech Recognition, Image Classification and Language Processing. It has been proved that through simulating human neural network and hierarchically (layer-by-layer) learning features from large scale data can significantly improve analytic results. In this project, we focus on developing multimedia retrieval approaches based on DL technologies. 

Current research topics:

Multimedia analysis and computer vision

  • End-to-end scene text detection and recognition in real-time using deep neural networks
  • Image/video captioning
  • Multimodal data retrieval
  • Deep Learning in medical image processing e.g. brain abnormality detection
  • Handwriting analysis in art historical data
  • Other computer vision applications

Research in deep learning algorithm

  • Efficient AI system with the focus on edge computing
  • Binary neural networks
  • Label noise, weakly supervised representation learning, label synthesis
  • Efficient deep models for NLP applications

Current Projects

KI-Leuchttürme project for environment, climate, nature and resources

EKAPEx: New efficient AI algorithms for innovative forecasting methods for extreme weather events (2023-2025)

HPI will act as the coordinator for the project and collaborate with machine learning experts from the Technical University of Munich (TUM) and atmospheric and meteorological experts from the GeoForschungsZentrum Potsdam (GFZ). The aim of the project is to develop AI-based precipitation forecasting for Germany, with a special emphasis on extreme weather events. To accomplish this, the team will develop the most efficient and powerful AI algorithms possible, while also significantly reducing resource consumption. Unique datasets, such as Integrated Water Vapor and Slant Integrated Water Vapor obtained from GNSS observations, will also be utilized to enhance forecasting capabilities. The project aims to develop an accessible platform that will contribute significantly to the improvement of climate adaptation measures and the sustainable use of AI.

The team will employ efficient designs of AI algorithms, such as few-shot learning, zero-shot learning, and open-set recognition methods, in order to decrease dependence on large amounts of data and manual annotation for weather forecasting. Additionally, neural networks will be applied that can operate with a lower bitrate by converting the parameters and intermediate results of the network from previous 32-bit models to a binary value with only one bit, while minimizing accuracy loss. The project will also specifically address power consumption of AI methods as a source of greenhouse gases.

Deep Learning for Enterprise NLP Applications

Project partner: SAP Conversational AI team (2017-2020)

In this project we will develop a framework for building general-applicable as well as domain-specific NLP models by using state-of-the-art deep learning technology. The research problem on textual representation learning will be studied intended to find the most efficient solution for deep neural network design, and system implementation. The evaluation protocol will be defined and developed for the qualitative and quantitative evaluation.

Project partner: SAP ICN Machine Learning team (2020-2022)

The recently emerged large-scale pre-trained language models based on the Transformer model, such as GPT-3 (175 billion parameters) and Switch Transformer (1600 billion parameters), have brought about a series of breakthroughs in many Natural Language Processing (NLP) tasks. However, the training of these large-scale models is computationally expensive. Moreover, these models generally have billions of parameters, making it challenging to conduct inference on resource-limited devices. In this project, we will dive into how such large scale models work, study different approaches to decrease their space and time complexity during training and inference, and evaluate them on different Natural Language Understanding (NLU) and Natural Language Generation (NLG) benchmarks.

Binary Neural Networks, Deep Model Compression and Acceleration

Project partner: PyTorch, NICSEFCMXNet

In recent years, deep learning technologies achieved excellent performance and many breakthroughs in both academia and industry. However the state-of-the-art deep models are computational expensive
and consume large storage space. Deep learning is also strongly demanded by numerous applications from areas such as mobile platforms, wearable devices, autonomous robots and IoT devices. How to efficiently apply deep models on such low power devices becomes a challenging research problem. In this project we will explore several different approaches such as binarized, quantized as well as lightweight deep neural networks for this problem. The development is based on well known open source deep learning library PyTorch and Apache MXNet. As a in progress research result we have developed two open source frameworks:

Project partner: Wildenstein Plattner Institute

With increasing digitization and storage capacities, it becomes more and more viable to undergo massive digitization projects for analogue archives. Digitization allows easy access and long term preservation of old and sensitive physical material, where access is typically denied. Furthermore, digitization allows the material to be processed more efficiently. In this project, we aim to develop and apply novel automatic processing methods for the digitized archive of the WPI. Since Archival material, especially in the art history domain, contains many images and handwriting, we concentrated on analysing and extracting handwritten information. Challenges, which should be addressed in this project are scalability and quality of different approaches for handwriting recognition. The digitization project that the WPI is undergoing covers a document corpus of many million pages in different fonts, languages and physical condition. 

Besides handwriting as one important type of semantic information in an archive, a digitized archive also contains many scans of documents that contain images. These images may be photographs, reproductions of works of art, or even sketches. A digitization pipeline would greatly benefit from additional analysis steps extracting metadata from such documents. In this line of work further analysis steps, such as classification of documentsby visual appearance, automatic creation of textual metadata (i.e. descriptions) of images, and recognition of depicted objects in images shall be added to the resulting digitization pipeline. All of the developed approaches shall be incorporated into a system usable by the researchers of the WPI by incorporation into their cataloguing software.

Intelligent Lecture Video Analysis and Retrieval

Project partner: tele-TASK and openHPI team

  • Video Lecture Browser: Lecture video content analysis, automatic video indexing, content-based video search, lecture speech recognition, lecture slides recognition.
  • Automatic E-Lecture Material Enhancement

Former Projects


 tele-TASK:(tele-Teaching Anywhere Solution Kit) is an advanced mobile system for the production of Internet streaming videos and podcasts featuring a new and drastically simplified technology.

 MEDIAGLOBE - the digital archive is part of the THESEUS research program initiated by the German Federal Ministry of Economy and Technology (BMWi). MEDIAGLOBE deals with digitization, analysis, and semantic retrieval of historical, documentary audiovisual content.

Research Team

  • Supervisor: Prof. Dr. Christoph Meinel 
  • Group leader: PD Dr. habil. Haojin Yang (G2-E.26)
  • Joseph Bethge (PhD student, G2-E.32) thesis submitted
  • Ting Hu (PhD student, G2-E.31) thesis submitted
  • Ziyun Li (PhD student, G2-E.31)
  • Nianhui Guo (PhD student, G2-E.32)
  • Jona Otholt (PhD student, G2-E.31)
  • Gregor Nickel (PhD student, G2-E.32)
  • Weixing Wang (PhD student, G2-E.32)
  • Hong Guo (PhD student, G2-E.31)
  • Zi Yang (co-supervised industry PhD student, Huawei Munich Research Center)
  • Maximilian Schulze (Scientific coworker
  • Philipp Hildebrandt (Scientific coworker)
  • Elena Gensch (Scientific coworker)
  • Cedric Lorenz (Scientific coworker)
  • Eszter Pai (Scientific coworker)
  • Mohammad Yakub (Scientific coworker)
  • Dimitrije Ristic (Scientific coworker)

Former Team Members

  • Dimitri Korsch (master studentnow PhD Student with Friedrich-Schiller-Universität Jena)
  • Hannes Rantzsch (master student, now with nexenio GmbH)
  • Tom Herold (master student, now with scalable minds)
  • Sheng Luo (PhD Student, now with Nvidia Shanghai)
  • Dr. Cheng Wang (PhD student, now with Amazon AI)
  • Martin Fritzsche (master student)
  • Haofang Lu (PhD student)
  • Dr. Xiaoyin Che (PhD student and PostDoc researcher, now with Siemens Research China)
  • Larissa Hoffäller (scientific coworker)
  • Julian Niedermeier (scientific coworker)
  • Jonathan Sauder (intern)
  • Dr. Mina Razaei (PhD student, now with LMU)
  • Dr. Goncalo Mordido (PhD student, now with MILA-Quebec AI Institute)
  • Benedikt Schenkel (scientific coworker)
  • Dr. Christian Bartz (PhD student, now with German Aerospace Center)
  • Hendrik Rätz (PhD student)
  • Axel Stebner (scientific coworker)
  • Prashant Dangwal (scientific coworker)
  • Paul Mattes (Scientific coworker)
  • Christopher Aust (Scientific coworker)



Reviewed Publications


In Journal:





  • Mina Rezaei, Haojin Yang and Christoph Meinel, "Recurrent generative adversarial network for learning imbalanced medical image semantic segmentation", International Journal of Multimedia Tools and Applications (MTAP), Special Issue: "Deep Learning for Computer-aided Medical Diagnosis", Online first version: https://doi.org/10.1007/s11042-019-7305-1, 07 Feb. 2019 online version


  • Cheng Wang, Haojin Yang and Christoph Meinel, "Image Captioning with Deep Bidirectional LSTMs and Multi-Task Learning", ACM Transactions on Multimedia Computing Communications and Applications (TOMM) 2018 [link][PDF][BibTex]


  • Xiaoyin Che, Haojin Yang, Christoph Meinel, "Automatic Online Lecture Highlighting Based on Multimedia Analysis", IEEE Transactions on Learning Technologies (TLT), Publisher: IEEE Computer Society and IEEE Education Society 2017, Volume: PP, Issue: 99, DOI: 10.1109/TLT.2017.2716372, Print ISSN: 1939-1382 [citation] [PDF]


  • Cheng Wang, Haojin Yang and Christoph Meinel, "A Deep Semantic Framework for Multimodal Representation Learning", International Journal of MULTIMEDIA TOOLS AND APPLICATIONS (MTAP), DOI: 10.1007/s11042-016-3380-8, online ISSN:1573-7721, Print ISSN:1380-7501,  Special Issue: "Representation Learning for Multimedia Data Understanding", March 2016 [link] [PDF] [BibTex]


  • Haojin Yang, Christoph Meinel, "Content Based Lecture Video Retrieval Using Speech and Video Text Information", IEEE TRANSACTIONS ON LEARNING TECHNOLOGIES (TLT), DIO: 10.1109/TLT.2014.2307305, online ISSN: 1939-1382, pp. 142-154, volume 7, number 2, April-June 2014, Publisher: IEEE Computer Society and IEEE Education Society [citation BibTex] [PDF]


In Conference, Workshop and arXiv: 


  • Guo, N., Bethge, J., Yang, H., Zhong, K., Ning, X., Meinel, C., & Wang, Y. (2024, February). BoolNet: Towards Energy-Efficient Binary Neural Networks Design and Optimization. In 2nd Workshop on Sustainable AI.
  • Wang, W., Yang, H., Meinel, C., Özkan, H. Y., Bermudez Serna, C., & Mas-Machuca, C. (2024). Feature Distribution Shift Mitigation with Contrastive Pretraining for Intrusion Detection. In Network Traffic Measurement and Analysis Conference.
  • Otholt, J., Meinel, C., & Yang, H. (2024). Guided Cluster Aggregation: A Hierarchical Approach to Generalized Category Discovery. In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (pp. 2618-2627).


  • Li, Z., Meinel, C., & Yang, H. (2023). Generalized Categories Discovery for Long-tailed Recognition. arXiv preprint arXiv:2401.05352.
  • Li, Z., Dai, B., Simsek, F., Meinel, C., & Yang, H. (2023). ImbaGCD: Imbalanced Generalized Category Discovery. arXiv preprint arXiv:2401.05353.
  • Hu, T., Meinel, C., & Yang, H. (2023). Scaled Prompt-Tuning for Few-Shot Natural Language Generation. arXiv preprint arXiv:2309.06759.
  • Hu, T., Meinel, C., & Yang, H. (2023, June). Flexible BERT with Width-and Depth-dynamic Inference. In 2023 International Joint Conference on Neural Networks (IJCNN) (pp. 1-8). IEEE.
  • Li, Z., Wang, X., Robertson, N. M., Clifton, D. A., Meinel, C., & Yang, H. (2023, June). SMKD: Selective Mutual Knowledge Distillation. In 2023 International Joint Conference on Neural Networks (IJCNN) (pp. 1-8). IEEE.
  • Hu, T., Meinel, C., & Yang, H. (2023, June). Boosting Bert Subnets with Neural Grafting. In ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (pp. 1-5). IEEE.
  • Simsek, F., Pfitzmann, B., Raetz, H., Otholt, J., Yang, H., & Meinel, C. (2023). DocLangID: Improving Few-Shot Training to Identify the Language of Historical Documents. arXiv preprint arXiv:2305.02208.


  • Guo, N., Bethge, J., Meinel, C., & Yang, H. (2022). Join the High Accuracy Club on ImageNet with A Binary Neural Network Ticket. arXiv preprint arXiv:2211.12933. [pdf] [code]
  • Hu, T., Meinel, C., & Yang, H. (2022). Empirical Evaluation of Post-Training Quantization Methods for Language Tasks. arXiv preprint arXiv:2210.16621. [pdf]
  • Li, Z., Wang, X., Meinel, C., Robertson, N. M., Clifton, D. A., & Yang, H. (2022, October). Not all knowledge is created equal: mutual distillation of confident knowledge. In NeurIPS 2022 Workshop on Trustworthy and Socially Responsible Machine Learning
  • Li, Z., Otholt, J., Dai, B., Meinel, C., & Yang, H. (2022). A Closer Look at Novel Class Discovery from the Labeled Set. arXiv preprint arXiv:2209.09120. [pdf] [code coming soon]
  • Bartz, C., Raetz, H., Otholt, J., Meinel, C., & Yang, H. (2022, August). Synthesis in Style: Semantic Segmentation of Historical Documents using Synthetic Data. In 2022 26th International Conference on Pattern Recognition (ICPR) (pp. 3878-3884). IEEE. [code] [pdf]


  • Bartz, C., Bethge, J., Yang, H., & Meinel, C. (2020). One Model to Reconstruct Them All: A Novel Way to Use the Stochastic Noise in StyleGAN. The 32nd British Machine Vision Conference (BMVC), 22nd - 25th November 2021 [pdf][code]
  • Hu, Ting, Haojin Yang, and Christoph Meinel. "Denoising AutoEncoder Based Delete and Generate Approach for Text Style Transfer." International Conference on Artificial Neural Networks. Springer, Cham, 2021. [pdf]
  • N Guo, J Bethge, H Yang, K Zhong, X Ning, C Meinel, Y Wang. (2021). BoolNet: Minimizing The Energy Consumption of Binary Neural Networks. arXiv preprint arXiv:2106.06991 [pdf][code][video]
  • Li, Z., Wang, X., Yang, H., Hu, D., Robertson, N. M., Clifton, D. A., & Meinel, C. (2021). Not All Knowledge Is Created Equal. arXiv preprint arXiv:2106.01489. [pdf][code] 
  • H Yang, Z Shen, Y Zhao, AsymmNet: Towards ultralight convolution neural networks using asymmetrical bottlenecks, MAI@CVPR 2021 [pdf][code][video]
  • G Mordido, H Yang, C Meinel, Evaluating Post-Training Compression in GANs using Locality-Sensitive Hashing, arXiv preprint arXiv:2103.11912 [pdf]
  • Bethge, J., Bartz, C., Yang, H., Meinel, C. An Improved Network Architecture for Binary Neural Networks, WACV 2021 [pdf] [code]


  • Bethge, J., Bartz, C., Yang, H., Meinel, C. (2020). MeliusNet: Can Binary Neural Networks Achieve MobileNet-level Accuracy?. arXiv preprint arXiv:2001.05936. [pdf][code]
  • Bartz, C., Bethge, J., Yang, H., & Meinel, C. (2020). One Model to Reconstruct Them All: A Novel Way to Use the Stochastic Noise in StyleGAN. arXiv preprint arXiv:2010.11113. [pdf][code]
  • Bartz, C., Bethge, J., Yang, H., & Meinel, C. (2020). KISS: Keeping It Simple for Scene Text Recognition. arXiv preprint arXiv:1911.08400. [pdf][code]
  • G. Mordido, H. Yang and C. Meinel.: microbatchGAN: Stimulating Diversity with Multi-Adversarial Discrimination. In IEEE Winter Conference on Application Computer Vision (WACV’20), Snowmass village, Colorado, March 2-5, 2020
  • J Bethge, C Bartz, H Yang, C Meinel, BMXNet 2: An Open Source Framework for Low-bit Networks-Reproducing, Understanding, Designing and Showcasing. In Proceedings of the 28th ACM International Conference on Multimedia, 2020 [PDF][code]
  • Jonathan Sauder, Ting Hu, Xiaoyin Che, Gonçalo Mordido, Haojin Yang, Christoph Meinel, Best student forcing: A simple training mechanism in adversarial language generation. In Proceedings of The 12th Language Resources and Evaluation Conference, 2020. [PDF] [code]
  • Bartz, C., Seidel, L., Nguyen, D. H., Bethge, J., Yang, H., & Meinel, C. Synthetic Data for the Analysis of Archival Documents: Handwriting Determination. DICTA 2020.


  • Bethge, J., Yang, H., Bornstein, M., & Meinel, C. BinaryDenseNet: Developing an Architecture for Binary Neural Networks. International Conference on Computer Vision (ICCV'19), Neural Architects'19, Oct. 27- Nov. 2 2019, Seoul, Korea
  • Bethge, J., Yang, H., Bornstein, M., & Meinel, C. Back to Simplicity: How to Train Accurate BNNs from Scratch?. arXiv preprint arXiv:1906.08637. [Demo] [code][pdf]
  • Joseph Bethge, Haojin Yang, Christoph Meinel, Training Accurate Binary Neural Networks From Scratch, In IEEE International Conference on Image Processing (ICIP'19) in Taipei, Taiwan, September 22-25, 2019
  • Mina Rezaei, Haojin Yang, Konstantine Harmuth, Christoph Meinel: Conditional Generative Adversarial Refinement Networks for Unbalanced Medical Image Semantic Segmentation. In IEEE Winter Conference on Application Computer Vision (WACV’19), pages:1836-1845, Waikoloa Village, HI, USA, January 7-11, 2019 [code]
  • Mina Rezaei, Haojin Yang, Christoph Meinel: Learning Imbalanced Semantic Segmentation through Cross-Domain Relations of Multi-Agent Generative Adversarial Networks. SPIE Medical Imaging - Computer Aided Diagnosis (SPIE’19), pages 1-6, San Diego, California, United States 16 - 21 February 2019


  • Jonathan Sauder, Xiaoyin Che, Gonçalo Mordido, Haojin Yang and Christoph Meinel. Pseudo-Ground-Truth Training for Adversarial Text Generation with Reinforcement Learning. Deep Reinforcement Learning Workshop at NeurIPS 2018 (Deep RL workshop)
  • Mina Rezaei, Haojin Yang, Christoph Meinel: Generative Adversarial Framework for Learning Multiple Clinical Tasks. Accepted by Machine Learning for Health Workshop at NeurIPS 2018 (ML4H)
  • Mina Rezaei, Haojin Yang and Christoph Meinel, Generative Adversarial Framework for Learning Multiple Clinical Tasks. Digital Image Computing: Techniques and Applications (DICTA 2018)
  • Christian Bartz, Haojin Yang, Joseph Bethge and Christoph Meinel. LoANs: Weakly Supervised Object Detection with Localizer Assessor Networks​. 1st International Workshop on Advanced Machine Vision for Real-life and Industrially Relevant Applications​" (AMV 2018), in conjunction with the "Asian Conference on Computer Vision" (ACCV) 2-6 December 2018, in Perth, Australia
  • Mina Rezaei, Haojin Yang, Christoph Meinel: voxel-GAN: Adversarial Framework for Learning Imbalanced Brain Tumor Segmentation. Accepted by BrainLes@MICCAI 2018, code)
  • G. Mordido, H. Yang and C. Meinel. Dropout-GAN: Learning from a Dynamic Ensemble of Discriminators. ACM KDD'18 Deep Learning Day (KDD DLDay 2018), London UK, 2018 [PDF]
  • Mina Rezaei, Haojin Yang and Christoph Meinel "Instance Tumor Segmentation using Multitask Convolutional Neural Network" International Joint Conference on Neural Networks (IJCNN) 2018   
  • Mina Rezaei, Haojin Yang, Christoph Meinel "Whole Heart and Great Vessel Segmentation with Context-aware of Generative Adversarial Networks" Bildverarbeitung für die Medizin (BVM) 2018
  • Mina Rezaei, Haojin Yang, Christoph Meinel, "Automatic Cardiac MRI Segmentation via Context-aware Recurrent Generative Adversarial Neural Network", Computer Assisted Radiology and Surgery (CARS 2018)


  • Chrisitian Bartz, Haojin Yang, Christoph Meinel "SEE: Towards Semi-Supervised End-to-End Scene text Recognition", the Thirty-Second AAAI Conference on Artificial Intelligence (AAAI-18), February 2–7, 2018 New Orleans, Lousiana, USA (PDF) (codes)
  • Chrisitian Bartz, Haojin Yang, Christoph Meinel “STN-OCR: A single Neural Network for Text Detection and Text Recognition”,  arXiv:1707.08831v1 2017 (codes)
  • Christian Bartz, Tom Herold, Haojin Yang and Christoph Meinel "Language Identification Using Deep Convolutional Recurrent Neural Networks", 24th International Conference on Neural Information Processing (ICONIP 2017), November 14-18, 2017, Guangzhou, China 
  • Mina Rezaei, Haojin Yang and Christoph Meinel "Deep Neural Network with l2-norm Unit for Brain Lesions Detection", 24th International Conference on Neural Information Processing (ICONIP 2017), November 14-18, 2017, Guangzhou, China 
  • Xiaoyin Che, Nico Ring, Willi Raschkowski, Haojin Yang and Christoph Meinel, "Traversal-Free Word Vector Evaluation in Analogy Space", RepEval workshop at EMNLP 17 (Empirical Methods in Natural Language Processing), September 7–11, 2017, Copenhagen, Denmark. [PDF copy]
  • Haojin Yang, Martin Fritzsche, Christian Bartz, Christoph Meinel, "BMXNet: An Open-Source Binary Neural Network Implementation Based on MXNet" ACM International Conference on Multimedia (ACM MM 2017), Open Source Software Competition, October 23-27, 2017, Mountain View, CA USA. [PDF] [project][Amazon AI Blog]
  • Xiaoyin Che, Nico Ring, Willi Raschkowski, Haojin Yang and Christoph Meinel "Automatic Lecture Subtitle Generation and How It Helps", 17th IEEE International Conference on Advanced Learning Technologies (ICALT 2017), July 3-7, 2017, Timisoara, Romania. [PDF copy][BibTex]


  • Haojin Yang, Cheng Wang, Christian Bartz, Christoph Meinel "SceneTextReg: A Real-Time Video OCR System", ACM international conference on Multimedia (ACM MM 2016), system demonstration session, 15-19 October 2016, Amsterdam, The Netherlands [PDF copy][demo video] [BibTex]
  • Cheng Wang, Haojin Yang, Christian Bartz, Christoph Meinel "Image Captioning with Deep Bidirectional LSTMs", ACM international conference on Multimedia (ACM MM 2016), full paper in the deep learning session of the main conference track, 15-19 October 2016, Amsterdam, The Netherlands [PDF copy] [demo video
  • Xiaoyin Che, Cheng Wang, Haojin Yang and Christoph Meinel, "Punctuation Prediction for Unsegmented Transcript Based on Word Vector", "the 10th International Conference on Language Resources and Evaluation (LREC 2016)", Portorož (Slovenia), 23-28 May 2016 [Dataset]
  • Haojin Yang, "Real-Time Video OCR System", system demonstration at 41st IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2016), Show&Tell session, Shanghai China, 20-25 March 2016
  • Cheng Wang, Haojin Yang and Christoph Meinel, "Exploring Multimodal Video Representation for Action Recognition", the annual International Joint Conference on Neural Networks (IJCNN 2016), Vancouver, Canada, July 24-29, 2016
  • Xiaoyin Che, Thomas Staubitz, Haojin Yang and Christoph Meinel, "Pre-Course Key Segment Analysis of Online Lecture Videos", 16th IEEE International Conference on Advancing Learning Technologies (ICALT-2016), Austin, Texas, USA, July 25-28, 2016
  • Xiaoyin Che, Sheng Luo, Haojin Yang and Christoph Meinel, "Sentence Boundary Detection Based on Parallel Lexical and Acoustic Models", INTERSPEECH 2016, San Francisco, California, USA in September 8-12, 2016 
  • Sheng Luo, Haojin Yang, Cheng Wang, Xiaoyin Che, and Christoph Meinel, "Action Recognition in Surveillance Video Using ConvNets and Motion History Image", International Conference on Artificial Neural Networks (ICANN 2016), Barcelona Spain, 6th-9th of September 2016 
  • Sheng Luo, Haojin Yang, Cheng Wang, Xiaoyin Che and Christoph Meinel, "Real-time action recognition in surveillance videos using ConvNets", in the 23rd International Conference on Neural Information Processing (ICONIP 2016), in Kyoto (Japan), 16th-21th of October 2016
  • Hannes Rantzsch, Haojin Yang and Christoph Meinel "Signature Embedding: Writer Independent Offline Signature Verification with Deep Metric Learning" in 12th International Symposium on Visual Computing (ISVC'16), Las Vegas USA, December 12-14, 2016. [PDF copy] [Poster]
  • Xiaoyin Che, Sheng Luo, Haojin Yang, Christoph Meinel "Sentence-Level Automatic Lecture Highlighting Based on Acoustic Analysis" 16th IEEE International Conference on Computer and Information Technology (IEEE CIT 2016), Shangri-La's Fijian Resort, Fiji, 7-10 December 2016


  • Cheng Wang, Haojin Yang, Xiaoyin Che and Christoph Meinel, "Concept-Based Multimodal Learning for Topic Generation", the 21st MultiMedia Modelling Conference (MMM2015), Sydney, Australia, Jan 5-7, 2015
  • Sheng Luo, Haojin Yang and Christoph Meinel, "Reward-based Intermittent Reinforcement in Gamification for E-learning", 7th International Conference on Computer Supported Education (CSEDU), Lisbon, Portugal, Mai 23-25, 2015
  • H.J.Yang, C.Wang, X.Y.Che, S.Luo and Ch.Meinel. “An Improved System For Real-Time Scene Text Recognition”, ACM International Conference on Multimedia Retrieval (ICMR 2015), system demonstration session, Shanghai, June 23-26, 2015
  • Cheng Wang, Haojin Yang and Christoph Meinel, "Does Multilevel Semantic Representation Improve Text Categorization?", the 26th International Conference on Database and Expert Systems Applications (DEXA 2015), Valencia, Spain, September 1-4, 2015
  • Cheng Wang, Haojin Yang and Christoph Meinel, "Visual-Textual Late Semantic Fusion Using Deep Neural Network for Document Categorization",  the 22nd International Conference on Neural Information Processing (ICONIP2015), Istanbul, Turkey, November 9-12, 2015
  • Cheng Wang, Haojin Yang, Christoph Meinel, "Deep Semantic Mapping for Cross-Modal Retrieval",  the 27th IEEE International Conference on Tools with Artificial Intelligence (ICTAI 2015), Vietri sul Mare, Italy, November 9-11, 2015
  • Xiaoyin Che, Haojin Yang and Christoph Meinel, "Adaptive E-Lecture Video Outline Extraction Based on Slides Analysis", the 14th International Conference on Web-based Learning (ICWL 2015), Guangzhou, China, November 5-8, 2015
  • Xiaoyin Che, Haojin Yang and Christoph Meinel, "Table Detection from Slide Images", 7th Pacific Rim Symposium on Image and Video Technology (PSIVT2015), 23-27 November, 2015, Auckland, New Zealand


  • Bernhard Quehl, Haojin Yang and Harald Sack, "Improving text recognition by distinguishing scene and overlay text", the 7th International Conference on Machine Vision (ICMV 2014), Milan, Italy, November 19-21, 2014


  • Xiaoyin Che, Haojin Yang, Christoph Meinel, "Lecture Video Segmentation by Automatically Analyzing the Synchronized Slides", The 21st ACM International Conference on Multimedia (ACM MM13), Grand Challenge: "Temporal Segmentation and Annotation Grand Challenge" October 21-25, 2013, Barcelona, Spain. [copy PDF]
  • Xiaoyin Che, Haojin Yang, Christoph Meinel, "Tree-Structure Outline Generation for Lecture Videos with Synchronized Slides", The Second International Conference on E-Learning and E-Technologies in Education (ICEEE2013), 23-25th September 2013, Lodz Poland. [copy PDF]
  • Franka Grünewald, Haojin Yang, Christoph Meinel, "Evaluating the Digital Manuscript Functionality - User Testing For Lecture Video Annotation Features", 12th International Conference on Web-based Learning (ICWL 2013), 6 - 9th October 2013,  Kenting, Taiwan. Springer lecture notes, 2013. (best student paper award) [copy PDF]
  • Haojin Yang, Franka Grünewald, Matthias Bauer, Christoph Meinel, "Lecture Video Browsing Using Multimodal Information Resources", 12th International Conference on Web-based Learning (ICWL 2013), 6 - 9th October 2013, Kenting, Taiwan. Springer lecture notes.
  • Franka Grünewald, Haojin Yang, Elnaz Mazandarani, Matthias Bauer and Christoph Meinel, "Next Generation Tele-Teaching: Latest Recording Tech- nology, User Engagement and Automatic Metadata Retrieval", International Conference on Human Factors in Computing and Informatics (southCHI), Lecture Notes in Computer Science (LNCS) Springer, 01–03 July, 2013 Maribor, Slovenia


  • Haojin Yang, Christoph Oehlke and Christoph Meinel, "An Automated Analysis and Indexing Framework for Lecture Video Portal", 11th International Conference on Web-based Learning (ICWL 2012), 2 - 4th September 2012,  Sinaia, Romania. Springer lecture notes, Volume 7558, 2012. [citation BibTex](accept rate:26%)(best student paper award)
  • Haojin Yang, Bernhard Quehl, Harald Sack, "A skeleton based binarization approach for video text recognition", 13th International Workshop on Image analysis for multimedia interactive services (WIAMIS 2012), 23rd - 25th May 2012, IEEE Press, Dublin Ireland. [poster] [citation BibTex]
  • C. Hentschel, J. Hercher, M. Knuth, J. Osterhoff, B. Quehl, H. Sack, N. Steinmetz, J. Waitelonis, H-J.Yang:
    "Open Up Cultural Heritage in Video Archives with Mediaglobe", 12th International Conference on Innovative Internet Community Services (I2CS 2012), June 13-15, 2012, Trondheim (Norway) [citation BibTex] (best paper award)
  • Haojin Yang, Franka Gruenewald and Christoph Meinel, "Automated extraction of lecture outlines from lecture videos: a hybrid solution for lecture video indexing", 4th International Conference on Computer Supported Education (CSEDU 2012) (indexation by Thomson Reuters Conference Proceedings Citation Index (ISI) and Elsevier Index (EI)), SciTePress, April. 16-18, 2012, Porto Portugal [citation BibTex] (accept rate: 12%)
  • Haojin Yang, Bernhard Quehl and Harald Sack, "Text detection in video images using adaptive edge detection and stroke width verification", 19th International Conference on Systems, Signals and Image Processing (IWSSIP 2012), IEEE Press, Vienna, Austria, April. 11-13, 2012 [citation BibTex]


  • Haojin Yang, Maria Siebert, Patrick Lühne, Harald Sack and Christoph Meinel, "Lecture Video Indexing and Analysis Using Video OCR Technology", 7th International Conference on Signal Image Technology and Internet Based Systems (SITIS 2011), Track Internet Based Computing and Systems, IEEE Press, Dijon (France), Nov.28 - Dec. 1, 2011. [citation BibTex]
  • Haojin Yang, Maria Siebert, Patrick Lühne, Harald Sack and Christoph Meinel, "Automatic Lecture Video Indexing Using Video OCR Technology" IEEE International Symposium on Multimedia 2011 (ISM 2011), IEEE Press, Dana Point, CA, USA, Dec. 5-7, 2011. [citation BibTex]
  • Haojin Yang, Christoph Oehlke and Christoph Meinel, "A Solution for German Speech Recognition for Analysis and Processing of Lecture Videos" 10th IEEE/ACIS International Conference on Computer and Information Science (ICIS 2011) , IEEE Press, Sanya, Heinan Island, China, May 2011 [citation BibTex]



Concluded PhD Theses

  • Dr. Cheng Wang: "Deep Learning of Multimodal Representations"
  • Dr. Xiaoyin Che: "E-Lecture Material Enhancement Based on Automatic Multimedia Analysis"
  • Dr. Mina Rezaei: "Deep representation Learning from Imbalanced Medical Imaging"
  • Dr. Goncalo Mordido: "Diversification, Compression, and Evaluation Methods for Generative Adversarial Networks"
  • Dr. Christian Barz: "Reducing the Annotation Burden: Deep Learning for Optical Character Recognition using less Manual Annotations"

Current Master Theses

Concluded Master Thesis

  • Furkan Simsek, "LTGCD: Long-tailed Generalized Category Discovery", 2023
  • Weixing Wang, "Network Intrusion Detection using pre-trained tabular representation models", co-supervision with Prof. Wolfgang Kellerer from TUM,2023
  • Jonas Krah, "Accelerating Monocular Depth Estimation using Binary Neural Networks", 2023
  • Tobias Bredow, "Synthetic Data for the Segmentation of Medical Images", 2022
  • Alexander Kromer, "Quantized Ensemble Neural Networks", 2022
  • Erik Ziegler, "Multi-Task and Zero-Shot Learning with Question Answering Transformer Models", 2022
  • Emanuel Metzenthin, "Weakly Supervised Text Localization using Deep Reinforcement Learning", 2022
  • Jona Otholt, "Automatic Categorization of Scanned Documents" 2021
  • Rätz, Hendrik "Handwriting Classification on Archival Documents using Deep Neural Networks", 2020
  • Julian Niedermeier, "Manifold Learning for the Evaluation of Generative Models" 2019
  • Wolff, Felix "Online Activity Prediction with Long-short-term Memory Recurrent Networks" (co-supervision with Prof. Mathias Weske and Dr. Luise Pufahl), 2019
  • Loy, Adrian "Adaptive Precision of Deep Neural Networks", 2019
  • Bornstein, Marvin "Evaluation of Quantized Deep Neural Networks", 2019
  • Meyer, Thorben "Handwriting Detection/Recognition from Art-Historical Documents", 2018
  • Tom Herold: "Language identification in audio files using deep learning", 2017
  • Martin Fritzsche: "Quantized Deep Neural Networks", 2017
  • Hannes Rantzsch: "A deep learning approach to signature verification", 2016
  • Dimitri Korsch: "Perspective recification of scene text with the help of analytical and deep learning approaches", 2016
  • Christian Bartz: "Scene text recognition using deep learning", 2016


    WS 2023/2024

    SS 2023

    WS 2022/2023

    SS 2022

    WS 2021/2022

    SS 2021

    WS 2020/2021

    • Master Seminar "Machine Intelligence with Deep Learning"

    SS 2019

    • Master Seminar: Practical Applications of Deep Learning

    WS 2018/2019

    • Master Seminar "Machine Intelligence with Deep Learning"

    SS 2018

    WS 2017/2018

    • Master Seminar "Machine Intelligence with Deep Learning"
    • Master Projekt "Nature Language Generation Using Generative Adversarial Networks"

    SS 2017

    • Master Seminar "Practical Video Analysis"
    • Bachelor Seminar: Weiterführende Themen zu Internet- und WWW-Technologien

    WS 2016/2017

    • Master Seminar "Practical Applications of Multimedia Retrieval"

    SS 2016

    • Master Seminar "Practical video analysis"
    • Bachelor Seminar: Weiterführende Themen zu Internet- und WWW-Technologien

    WS 2015/2016

    • Master Seminar "Practical Applications of Multimedia Retrieval"

    SS 2015

    • Master Seminar: Practical video analysis
    • Master Project: Video Classification with Convolutional Neural Networks
    • Bachelor Seminar: Weiterführende Themen zu Internet- und WWW-Technologien

    SS 2014

    • Master Seminar: Weiterführende Themen zu Internet- und WWW-Technologien

    SS 2013

    • Bachelor Seminar: Weiterführende Themen zu Internet- und WWW-Technologien

    WS 2012/2013

    • Bachelor Seminar: Web-Programmierung und Web-Frameworks 

    SS 2012

    • Bachelor seminar: Multimedia Analysis
    • Bachelorprojekt: "tele-TASK for Kids - Integration von tele-TASK in den Schulalltag"

    WS 2011/12

    • Master seminar: Large Scale Processing for Multimedia Analysis

    SS 2011

    • Bachelor seminar: Multimedia Analysis

    SS 2010

    • Bachelor seminar: Multimedia Analysis

    Professional Activities

    Program Committee Member and Reviewer

    • ICML 2024
    • ICLR 2024
    • NeurIPS 2023 
    • ICML 2023
    • ICLR 2023
    • AAAI 2023 (Senior PC)
    • NeurIPS 2022 
    • ICML 2022 (Senior PC)
    • ICLR 2022 (Highlighted Reviewer)
    • NeurIPS 2021
    • ICCV 2021
    • ICML 2021
    • CVPR 2021
    • NeurlPS 2020 (top 10% high scored reviewer)
    • ICML 2020
    • NeurlPS 2019 (top 35% high scored reviewer)
    • NLPCC Workshop on Explainable Artificial Intelligence 2019
    • IEEE Transactions on Neural Networks and Learning Systems 2019
    • IEEE Transactions on Multimedia 2018
    • International Journal on Signal Processing: Image Communication 2017
    • ACM Computing Surveys 2017
    • IEEE Transactions on Multimedia 2016
    • Neurocomputing 2016
    • Computer Vision and Image Understanding 2016
    • Computer Vision and Image Understanding 2015
    • Neurocomputing 2015
    • IET Image Processing 2015
    • IEEE Transactions on Image Processing 2015
    • ACM International Conference on LEARNING @SCALE 2014
    • African Journal of Business Management
    • Computer Vision and Image Understanding 2014
    • Neurocomputing 2014
    • ACM ICMR 2013
    • ICIP 2013
    • ICIP 2012